List of usage examples for org.apache.hadoop.fs FileStatus isDirectory
public boolean isDirectory()
From source file:cn.ict.magicube.fs.shell.FixedLs.java
License:Apache License
@Override protected void processPath(PathData item) throws IOException { FileStatus stat = item.stat; String line = String.format(lineFormat, (stat.isDirectory() ? "d" : "-"), stat.getPermission(), (stat.isFile() ? stat.getReplication() : "-"), formatSize(stat.getLen()), dateFormat.format(new Date(stat.getModificationTime())), item); out.println(line);/*from w w w . j ava2s . c o m*/ }
From source file:co.cask.cdap.data.stream.StreamInputSplitFinder.java
License:Apache License
/** * Get the input splits for a stream.//w w w . ja v a 2 s. c om * * @param conf Configuration of the filesystem the stream resides on. * @return List of input splits for the stream. * @throws IOException */ public List<T> getSplits(Configuration conf) throws IOException { List<T> splits = Lists.newArrayList(); // Collects all stream event files timestamp, size and block locations information // First grab all directories (partition) that matches with the time range. FileSystem fs = path.getFileSystem(conf); for (FileStatus partitionStatus : fs.listStatus(path)) { // partition should be directory String pathName = partitionStatus.getPath().getName(); if (!partitionStatus.isDirectory() || !StreamUtils.isPartition(pathName)) { continue; } // Match the time range long partitionStartTime = StreamUtils.getPartitionStartTime(pathName); long partitionEndTime = StreamUtils.getPartitionEndTime(pathName); if (partitionStartTime > endTime || partitionEndTime <= startTime) { continue; } // Collects all bucket file status in the partition. Collection<StreamDataFileSplitter> eventFiles = collectBuckets(fs, partitionStatus.getPath()); // For each bucket inside the partition directory, compute the splits for (StreamDataFileSplitter splitter : eventFiles) { splitter.computeSplits(fs, minSplitSize, maxSplitSize, startTime, endTime, splits, splitFactory); } } return splits; }
From source file:co.cask.cdap.data.tools.ReplicationStatusTool.java
License:Apache License
private static void addAllDirFiles(Path filePath, FileSystem fs, List<String> fileList) throws IOException { FileStatus[] fileStatus = fs.listStatus(filePath); for (FileStatus fileStat : fileStatus) { if (fileStat.isDirectory()) { addAllDirFiles(fileStat.getPath(), fs, fileList); } else {/*from w w w. j a va2 s .co m*/ fileList.add(fileStat.getPath().toString()); } } }
From source file:co.cask.cdap.internal.app.runtime.batch.dataset.partitioned.DynamicPartitioningOutputCommitter.java
License:Apache License
/** * Merge two paths together. Anything in from will be moved into to, if there * are any name conflicts while merging the files or directories in from win. * @param fs the File System to use/*from www . j a va 2s .c om*/ * @param from the path data is coming from. * @param to the path data is going to. * @throws IOException on any error */ private void mergePaths(FileSystem fs, final FileStatus from, final Path to) throws IOException { if (from.isFile()) { if (fs.exists(to)) { if (!fs.delete(to, true)) { throw new IOException("Failed to delete " + to); } } if (!fs.rename(from.getPath(), to)) { throw new IOException("Failed to rename " + from + " to " + to); } } else if (from.isDirectory()) { if (fs.exists(to)) { FileStatus toStat = fs.getFileStatus(to); if (!toStat.isDirectory()) { if (!fs.delete(to, true)) { throw new IOException("Failed to delete " + to); } if (!fs.rename(from.getPath(), to)) { throw new IOException("Failed to rename " + from + " to " + to); } } else { //It is a directory so merge everything in the directories for (FileStatus subFrom : fs.listStatus(from.getPath())) { Path subTo = new Path(to, subFrom.getPath().getName()); mergePaths(fs, subFrom, subTo); } } } else { //it does not exist just rename if (!fs.rename(from.getPath(), to)) { throw new IOException("Failed to rename " + from + " to " + to); } } } }
From source file:co.nubetech.hiho.dedup.TestDedupJob.java
License:Apache License
@Test public void testDedupByValueWithDelimitedTextInputFormat() throws Exception { final String inputData1 = "Xavier Wilson,Mason Holloway,Carlos Johnston,Martin Noel,Drake Mckinney\n" + "Drake Mckinney,Murphy Baird,Theodore Lindsey,Nehru Wilcox,Harper Klein\n" + "Kennedy Bailey,Jerome Perry,David Cabrera,Edan Fleming,Orlando Tyson"; final String inputData2 = "Zephania Bauer,Jermaine Gordon,Vincent Moon,Steven Pierce,Jasper Campos\n" + "Drake Mckinney,Murphy Baird,Theodore Lindsey,Nehru Wilcox,Harper Klein\n" + "Kennedy Bailey,Plato Atkinson,Stuart Guy,Rooney Levy,Judah Benson"; createTextFileInHDFS(inputData1, "/input1", "testFile1.txt"); createTextFileInHDFS(inputData2, "/input2", "testFile2.txt"); String[] args = new String[] { "-inputFormat", "co.nubetech.hiho.dedup.DelimitedTextInputFormat", "-inputKeyClassName", "org.apache.hadoop.io.Text", "-inputValueClassName", "org.apache.hadoop.io.Text", "-inputPath", "/input1,/input2", "-outputPath", "output", "-delimeter", ",", "-column", "1", "-dedupBy", "value" }; DedupJob job = runDedupJob(args);//from www . java 2 s.c om assertEquals(6, job.getTotalRecordsRead()); assertEquals(0, job.getBadRecords()); assertEquals(5, job.getOutput()); assertEquals(1, job.getDuplicateRecords()); FileSystem outputFS = getFileSystem(); Path outputPath = new Path(outputFS.getHomeDirectory(), "output"); FileStatus[] status = outputFS.listStatus(outputPath, getOutputPathFilter()); assertTrue(outputFS.exists(outputPath)); List<String> expectedOutput = new ArrayList<String>(); expectedOutput.add("Xavier Wilson,Mason Holloway,Carlos Johnston,Martin Noel,Drake Mckinney"); expectedOutput.add("Zephania Bauer,Jermaine Gordon,Vincent Moon,Steven Pierce,Jasper Campos"); expectedOutput.add("Drake Mckinney,Murphy Baird,Theodore Lindsey,Nehru Wilcox,Harper Klein"); expectedOutput.add("Kennedy Bailey,Jerome Perry,David Cabrera,Edan Fleming,Orlando Tyson"); expectedOutput.add("Kennedy Bailey,Plato Atkinson,Stuart Guy,Rooney Levy,Judah Benson"); int count = 0; for (FileStatus fileStat : status) { logger.debug("File status is " + fileStat.getPath() + " and is it a dir? " + fileStat.isDirectory()); FSDataInputStream in = outputFS.open(fileStat.getPath()); String line = null; while ((line = in.readLine()) != null) { logger.debug("Output is " + line); assertTrue("Matched output " + line, expectedOutput.contains(line)); expectedOutput.remove(line); count++; } in.close(); } assertEquals(5, count); }
From source file:co.nubetech.hiho.dedup.TestDedupJob.java
License:Apache License
@Test public void testDedupByValueWithTextInputFormat() throws Exception { final String inputData1 = "Xavier Wilson,Mason Holloway,Carlos Johnston,Martin Noel,Drake Mckinney\n" + "Drake Mckinney,Murphy Baird,Theodore Lindsey,Nehru Wilcox,Harper Klein\n" + "Kennedy Bailey,Jerome Perry,David Cabrera,Edan Fleming,Orlando Tyson"; final String inputData2 = "Zephania Bauer,Jermaine Gordon,Vincent Moon,Steven Pierce,Jasper Campos\n" + "Drake Mckinney,Murphy Baird,Theodore Lindsey,Nehru Wilcox,Harper Klein\n" + "Kennedy Bailey,Plato Atkinson,Stuart Guy,Rooney Levy,Judah Benson"; createTextFileInHDFS(inputData1, "/input1", "testFile1.txt"); createTextFileInHDFS(inputData2, "/input2", "testFile2.txt"); String[] args = new String[] { "-inputFormat", "org.apache.hadoop.mapreduce.lib.input.TextInputFormat", "-inputPath", "/input1,/input2", "-outputPath", "output", "-outputFormat", "co.nubetech.hiho.mapreduce.lib.output.NoKeyOnlyValueOutputFormat", "-dedupBy", "value" }; DedupJob job = runDedupJob(args);//from w w w .j a v a2 s . co m assertEquals(6, job.getTotalRecordsRead()); assertEquals(0, job.getBadRecords()); assertEquals(5, job.getOutput()); assertEquals(1, job.getDuplicateRecords()); FileSystem outputFS = getFileSystem(); Path outputPath = new Path(outputFS.getHomeDirectory(), "output"); FileStatus[] status = outputFS.listStatus(outputPath, getOutputPathFilter()); assertTrue(outputFS.exists(outputPath)); List<String> expectedOutput = new ArrayList<String>(); expectedOutput.add("Xavier Wilson,Mason Holloway,Carlos Johnston,Martin Noel,Drake Mckinney"); expectedOutput.add("Zephania Bauer,Jermaine Gordon,Vincent Moon,Steven Pierce,Jasper Campos"); expectedOutput.add("Drake Mckinney,Murphy Baird,Theodore Lindsey,Nehru Wilcox,Harper Klein"); expectedOutput.add("Kennedy Bailey,Jerome Perry,David Cabrera,Edan Fleming,Orlando Tyson"); expectedOutput.add("Kennedy Bailey,Plato Atkinson,Stuart Guy,Rooney Levy,Judah Benson"); int count = 0; for (FileStatus fileStat : status) { logger.debug("File status is " + fileStat.getPath() + " and is it a dir? " + fileStat.isDirectory()); FSDataInputStream in = outputFS.open(fileStat.getPath()); String line = null; while ((line = in.readLine()) != null) { logger.debug("Output is " + line); assertTrue("Matched output " + line, expectedOutput.contains(line)); expectedOutput.remove(line); count++; } in.close(); } assertEquals(5, count); }
From source file:co.nubetech.hiho.dedup.TestDedupJob.java
License:Apache License
@Test public void testDedupByValueWithSequenceFileAsTextInputFormat() throws Exception { HashMap<Text, Text> inputData1 = new HashMap<Text, Text>(); inputData1.put(new Text("1"), new Text("Xavier Wilson,Mason Holloway,Carlos Johnston,Martin Noel,Drake Mckinney")); inputData1.put(new Text("2"), new Text("Kennedy Bailey,Jerome Perry,David Cabrera,Edan Fleming,Orlando Tyson")); inputData1.put(new Text("3"), new Text("Drake Mckinney,Murphy Baird,Theodore Lindsey,Nehru Wilcox,Harper Klein")); createSequenceFileInHdfs(inputData1, "/input1", "testFile1.seq"); HashMap<Text, Text> inputData2 = new HashMap<Text, Text>(); inputData2.put(new Text("1"), new Text("Zephania Bauer,Jermaine Gordon,Vincent Moon,Steven Pierce,Jasper Campos")); inputData2.put(new Text("2"), new Text("Kennedy Bailey,Plato Atkinson,Stuart Guy,Rooney Levy,Judah Benson")); inputData2.put(new Text("4"), new Text("Drake Mckinney,Murphy Baird,Theodore Lindsey,Nehru Wilcox,Harper Klein")); createSequenceFileInHdfs(inputData2, "/input2", "testFile2.seq"); String[] args = new String[] { "-inputFormat", "org.apache.hadoop.mapreduce.lib.input.SequenceFileAsTextInputFormat", "-outputFormat", "co.nubetech.hiho.mapreduce.lib.output.NoKeyOnlyValueOutputFormat", "-inputPath", "/input1,/input2", "-outputPath", "output", "-inputKeyClassName", "org.apache.hadoop.io.Text", "-inputValueClassName", "org.apache.hadoop.io.Text", "-dedupBy", "value" }; DedupJob job = runDedupJob(args);// w w w.j ava 2 s. c om assertEquals(6, job.getTotalRecordsRead()); assertEquals(0, job.getBadRecords()); assertEquals(5, job.getOutput()); assertEquals(1, job.getDuplicateRecords()); FileSystem outputFS = getFileSystem(); Path outputPath = new Path(outputFS.getHomeDirectory(), "output"); FileStatus[] status = outputFS.listStatus(outputPath, getOutputPathFilter()); assertTrue(outputFS.exists(outputPath)); List<String> expectedOutput = new ArrayList<String>(); expectedOutput.add("Xavier Wilson,Mason Holloway,Carlos Johnston,Martin Noel,Drake Mckinney"); expectedOutput.add("Kennedy Bailey,Jerome Perry,David Cabrera,Edan Fleming,Orlando Tyson"); expectedOutput.add("Drake Mckinney,Murphy Baird,Theodore Lindsey,Nehru Wilcox,Harper Klein"); expectedOutput.add("Zephania Bauer,Jermaine Gordon,Vincent Moon,Steven Pierce,Jasper Campos"); expectedOutput.add("Kennedy Bailey,Plato Atkinson,Stuart Guy,Rooney Levy,Judah Benson"); int count = 0; for (FileStatus fileStat : status) { logger.debug("File status is " + fileStat.getPath() + " and is it a dir? " + fileStat.isDirectory()); FSDataInputStream in = outputFS.open(fileStat.getPath()); String line = null; while ((line = in.readLine()) != null) { logger.debug("Output is " + line); assertTrue("Matched output " + line, expectedOutput.contains(line)); expectedOutput.remove(line); count++; } in.close(); } assertEquals(5, count); }
From source file:co.nubetech.hiho.job.TestDBQueryInputJobWithCluster.java
License:Apache License
@Test public void testBasicTableImport() throws Exception { DBQueryInputJob job = new DBQueryInputJob(); String[] args = new String[] { "-jdbcDriver", "org.hsqldb.jdbcDriver", "-jdbcUrl", "jdbc:hsqldb:hsql://localhost/URLAccess", // "-jdbcUsername", "", // "-jdbcPassword", "", "-outputPath", "testBasicTableImport", "-outputStrategy", "delimited", "-delimiter", "DELIM", "-numberOfMappers", "2", "-inputTableName", "Pageview", "-inputOrderBy", "pageview" }; int res = ToolRunner.run(createJobConf(), job, args); assertEquals(0, res);/*www . j a v a 2s . c o m*/ //lets verify the result now FileSystem outputFS = getFileSystem(); //Path outputPath = getOutputDir(); Path outputPath = new Path(outputFS.getHomeDirectory(), "testBasicTableImport"); FileStatus[] status = outputFS.listStatus(outputPath, getOutputPathFilter()); assertTrue(outputFS.exists(outputPath)); List<String> expectedOutput = new ArrayList<String>(); expectedOutput.add("/aDELIM1000"); expectedOutput.add("/bDELIM2000"); expectedOutput.add("/cDELIM3000"); expectedOutput.add("/dDELIM4000"); expectedOutput.add("/eDELIM5000"); expectedOutput.add("/fDELIM6000"); expectedOutput.add("/gDELIM7000"); expectedOutput.add("/hDELIM8000"); expectedOutput.add("/iDELIM9000"); expectedOutput.add("/jDELIM10000"); int count = 0; for (FileStatus fileStat : status) { logger.debug("File status is " + fileStat.getPath() + " and is it a dir? " + fileStat.isDirectory()); FSDataInputStream in = outputFS.open(fileStat.getPath()); String line = null; while ((line = in.readLine()) != null) { logger.debug("Output is " + line); assertTrue("Matched output " + line, expectedOutput.contains(line)); expectedOutput.remove(line); count++; } in.close(); } assertEquals(10, count); }
From source file:co.nubetech.hiho.job.TestDBQueryInputJobWithCluster.java
License:Apache License
@Test public void testQueryBasedImport() throws Exception { DBQueryInputJob job = new DBQueryInputJob(); String[] args = new String[] { "-jdbcDriver", "org.hsqldb.jdbcDriver", "-jdbcUrl", "jdbc:hsqldb:hsql://localhost/URLAccess", "-outputPath", "testQueryBasedImport", "-inputQuery", "select url,pageview,commentCount from Pageview, PageComment where Pageview.url = PageComment.url", "-inputBoundingQuery", "select min(commentCount), max(commentCount) from PageComment", "-outputStrategy", "delimited", "-delimiter", "DELIM", "-numberOfMappers", "2", "-inputOrderBy", "Pageview.pageview" }; int res = ToolRunner.run(createJobConf(), job, args); assertEquals(0, res);/*from w ww . ja v a 2 s. c om*/ //lets verify the result now FileSystem outputFS = getFileSystem(); Path outputPath = new Path(outputFS.getHomeDirectory(), "testQueryBasedImport"); FileStatus[] status = outputFS.listStatus(outputPath, getOutputPathFilter()); assertTrue(outputFS.exists(outputPath)); List<String> expectedOutput = new ArrayList<String>(); expectedOutput.add("/aDELIM1000DELIM10"); expectedOutput.add("/bDELIM2000DELIM10"); expectedOutput.add("/cDELIM3000DELIM10"); expectedOutput.add("/dDELIM4000DELIM10"); expectedOutput.add("/eDELIM5000DELIM10"); expectedOutput.add("/fDELIM6000DELIM10"); expectedOutput.add("/gDELIM7000DELIM10"); expectedOutput.add("/hDELIM8000DELIM10"); expectedOutput.add("/iDELIM9000DELIM10"); expectedOutput.add("/jDELIM10000DELIM10"); int count = 0; for (FileStatus fileStat : status) { logger.debug("File status is " + fileStat.getPath() + " and is it a dir? " + fileStat.isDirectory()); FSDataInputStream in = outputFS.open(fileStat.getPath()); String line = null; while ((line = in.readLine()) != null) { logger.debug("Output is " + line); assertTrue("Matched output " + line, expectedOutput.contains(line)); expectedOutput.remove(line); count++; } in.close(); } assertEquals(10, count); }
From source file:co.nubetech.hiho.merge.TestMergeJob.java
License:Apache License
@Test public void testMergeByKeyWithDelimitedTextInputFormat() throws Exception { final String inputData1 = "Macon Kent,6269 Aenean St.,1-247-399-1051,08253" + "\nDale Zamora,521-7792 Mauris Rd.,1-214-625-6970,90510" + "\nCharles Wood,525-9709 In Rd.,1-370-528-4758,62714"; final String inputData2 = "Dale Zamora,521-7792 Mauris Rd.,1-214-625-6970,90510" + "\nMacaulay Jackson,5435 Dui. Avenue,1-770-395-6446,31584" + "\nCharles Wood,525-9709 In Rd.,1-370-528-4758,62714"; createTextFileInHDFS(inputData1, "/input1", "testFile1.txt"); createTextFileInHDFS(inputData2, "/input2", "testFile2.txt"); String[] args = new String[] { "-newPath", "/input1", "-oldPath", "/input2", "-mergeBy", "key", "-outputPath", "output", "-inputFormat", "co.nubetech.hiho.dedup.DelimitedTextInputFormat", "-inputKeyClassName", "org.apache.hadoop.io.Text", "-inputValueClassName", "org.apache.hadoop.io.Text" }; MergeJob job = runMergeJobs(args);// w ww .ja v a 2 s. c om assertEquals(3, job.getTotalRecordsNew()); assertEquals(3, job.getTotalRecordsOld()); assertEquals(0, job.getBadRecords()); assertEquals(4, job.getOutput()); FileSystem outputFS = getFileSystem(); Path outputPath = new Path(outputFS.getHomeDirectory(), "output"); FileStatus[] status = outputFS.listStatus(outputPath, getOutputPathFilter()); assertTrue(outputFS.exists(outputPath)); List<String> expectedOutput = new ArrayList<String>(); expectedOutput.add("Macon Kent,6269 Aenean St.,1-247-399-1051,08253"); expectedOutput.add("Dale Zamora,521-7792 Mauris Rd.,1-214-625-6970,90510"); expectedOutput.add("Charles Wood,525-9709 In Rd.,1-370-528-4758,62714"); expectedOutput.add("Macaulay Jackson,5435 Dui. Avenue,1-770-395-6446,31584"); int count = 0; for (FileStatus fileStat : status) { logger.debug("File status is " + fileStat.getPath() + " and is it a dir? " + fileStat.isDirectory()); FSDataInputStream in = outputFS.open(fileStat.getPath()); String line = null; while ((line = in.readLine()) != null) { logger.debug("Output is " + line); assertTrue("Matched output " + line, expectedOutput.contains(line)); expectedOutput.remove(line); count++; } in.close(); } assertEquals(4, count); }